Repositorio Nacional

Introduction: Smallholder farmers in Sub-Saharan Africa (SSA) are increasingly producing soybean for food, feed, cash, and soil fertility improvement. Yet, the difference between the smallholder farmers’ yield and either the attainable in research fields or the potential from crop models is wide. Reasons for the yield gap include low to nonapplication of appropriate fertilizers and inoculants, late planting, low plant populations, recycling seeds, etc. Methods: Here, we reviewed the literature on the yield gap and the technologies for narrowing it and modelled yields through the right sowing dates and suitable high-yielding varieties in APSIM. Results and Discussion: Results highlighted that between 2010 and 2020 in SSA, soybean production increased; however, it was through an expansion in the cropped area rather than a yield increase per hectare. Also, the actual smallholder farmers’ yield was 3.8, 2.2, and 2.3 times lower than the attainable yield in Malawi, Zambia, and Mozambique, respectively. Through inoculants, soybean yield increased by 23.8%. Coupling this with either 40 kg ha−1 of P or 60 kg ha−1 of K boosted the yields by 89.1% and 26.0%, respectively. Overall, application of 21–30 kg ha-1 of P to soybean in SSA could increase yields by about 48.2%. Furthermore, sowing at the right time increased soybean yield by 300%. Although these technologies enhance soybean yields, they are not fully embraced by smallholder farmers. Hence, refining and bundling them in a digital advisory tool will enhance the availability of the correct information to smallholder farmers at the right time and improve soybean yields per unit area.

Decision Support Tools Digital Tools Site-Specific Recommendations CIENCIAS AGROPECUARIAS Y BIOTECNOLOGÍA DECISION SUPPORT SYSTEMS LEGUMES YIELDS SOYBEANS

Identification of genetic loci for grain yield-related traits in the wheat population Zhongmai 578/Jimai 22

Jingyang Tong Ming Li xianchun xia Zhonghu He Yong Zhang (2023, [Artículo])

Grain Yield KASP Marker QTL Mapping SNP Chip CIENCIAS AGROPECUARIAS Y BIOTECNOLOGÍA GRAIN YIELDS QUANTITATIVE TRAIT LOCI MAPPING SINGLE NUCLEOTIDE POLYMORPHISMS WHEAT BREEDING

Big data, small explanatory and predictive power: Lessons from random forest modeling of on-farm yield variability and implications for data-driven agronomy

Martin van Ittersum (2023, [Artículo])

Context: Collection and analysis of large volumes of on-farm production data are widely seen as key to understanding yield variability among farmers and improving resource-use efficiency. Objective: The aim of this study was to assess the performance of statistical and machine learning methods to explain and predict crop yield across thousands of farmers’ fields in contrasting farming systems worldwide. Methods: A large database of 10,940 field-year combinations from three countries in different stages of agricultural intensification was analyzed. Random effects models were used to partition crop yield variability and random forest models were used to explain and predict crop yield within a cross-validation scheme with data re-sampling over space and time. Results: Yield variability in relative terms was smallest for wheat and barley in the Netherlands and for wheat in Ethiopia, intermediate for rice in the Philippines, and greatest for maize in Ethiopia. Random forest models comprising a total of 87 variables explained a maximum of 65 % of cereal yield variability in the Netherlands and less than 45 % of cereal yield variability in Ethiopia and in the Philippines. Crop management related variables were important to explain and predict cereal yields in Ethiopia, while predictive (i.e., known before the growing season) climatic variables and explanatory (i.e., known during or after the growing season) climatic variables were most important to explain and predict cereal yield variability in the Philippines and in the Netherlands, respectively. Finally, model cross-validation for regions or years not seen during model training reduced the R2 considerably for most crop x country combinations, while for wheat in the Netherlands this was model dependent. Conclusion: Big data from farmers’ fields is useful to explain on-farm yield variability to some extent, but not to predict it across time and space. Significance: The results call for moderate expectations towards big data and machine learning in agronomic studies, particularly for smallholder farms in the tropics where model performance was poorest independently of the variables considered and the cross-validation scheme used.

Model Accuracy Model Precision Linear Mixed Models CIENCIAS AGROPECUARIAS Y BIOTECNOLOGÍA MACHINE LEARNING SUSTAINABLE INTENSIFICATION BIG DATA YIELDS MODELS AGRONOMY

Testing innovations for adoption of newer and more adapted maize varieties

Michael Ndegwa Pieter Rutsaert Jason Donovan Jordan Chamberlin (2023, [Objeto de congreso])

Changing Production Conditions Genetic Innovations Maize Hybrids CIENCIAS AGROPECUARIAS Y BIOTECNOLOGÍA TESTING MAIZE VARIETIES YIELDS FARMERS EXPERIMENTATION

Enhancing maize yield in a conservation agriculture-based maize (Zea mays)- wheat (Triticum aestivum) system through efficient nitrogen management

C.M. Parihar Hari Sankar Nayak Dipaka Ranjan Sena Shankar Lal Jat Mahesh Gathala Upendra Singh (2023, [Artículo])

This study evaluated the impact of contrasting tillage and nitrogen management options on the growth, yield attributes, and yield of maize (Zea mays L.) in a conservation agriculture (CA)-based maize-wheat (Triticum aestivum L.) system. The field experiment was conducted during the rainy (kharif) seasons of 2020 and 2021 at the research farm of ICAR-Indian Agricultural Research Institute (IARI), New Delhi. The experiment was conducted in a split plot design with three tillage practices [conventional tillage with residue (CT), zero tillage with residue (ZT) and permanent beds with residue (PB)] as main plot treatments and in sub-plots five nitrogen management options [Control (without N fertilization), recommended dose of N @150 kg N/ha, Green Seeker-GS based application of split applied N, N applied as basal through urea super granules-USG + GS based application and 100% basal application of slow release fertilizer (SRF) @150 kg N/ha] with three replications. Results showed that both tillage and nitrogen management options had a significant impact on maize growth, yield attributes, and yield in both seasons. However, time to anthesis and physiological maturity were not significantly affected. Yield attributes were highest in the permanent beds and zero tillage plots, with similar numbers of grains per cob (486.1 and 468.6). The highest leaf area index (LAI) at 60 DAP was observed in PB (5.79), followed by ZT(5.68) and the lowest was recorded in CT (5.25) plots. The highest grain yield (2-year mean basis) was recorded with permanent beds plots (5516 kg/ha), while the lowest

was observed with conventional tillage (4931 kg/ha). Therefore, the study highlights the importance of CA practices for improving maize growth and yield, and suggests that farmers can achieve better results through the adoption of CA-based permanent beds and use of USG as nitrogen management option.

Green Seeker Urea Super Granules CIENCIAS AGROPECUARIAS Y BIOTECNOLOGÍA MAIZE UREA YIELDS ZERO TILLAGE NITROGEN

Seasonal climate forecasts (SCFs) based risk management strategies: A case study of rainfed rice cultivation in India

Nand Lal Kushwaha Paresh Shirsath Dipaka Ranjan Sena (2022, [Artículo])

FResampler1 Seasonal Climate Forecasts Decision Support System for Agrotechnology Transfer CIENCIAS AGROPECUARIAS Y BIOTECNOLOGÍA CLIMATE CHANGE DECISION SUPPORT SYSTEMS YIELDS RICE RISK MANAGEMENT